Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the start of sections or paragraphs indicated by special tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.91
     utafitiHapana
    -0.82
    ectoria
    -0.76
     PES
    -0.74
     Maradona
    -0.73
     scolas
    -0.73
    AntiForgeryToken
    -0.72
     Abbé
    -0.71
     unknownFields
    -0.69
    betic
    -0.68
    POSITIVE LOGITS
    Вам
    0.58
     to
    0.57
    дям
    0.56
     artikkelen
    0.55
    </strong>
    0.55
     Tribut
    0.55
    nek
    0.54
     ול
    0.54
    Всем
    0.54
    Gilles
    0.53
    Act Density 0.004%

    No Known Activations